Incorporating Dictionaries into a Neural Network Architecture to Extract COVID-19 Medical Concepts From Social Media

TL;DR

This paper demonstrates that integrating small domain-specific dictionaries into neural network models significantly enhances COVID-19 medical concept extraction from social media, with good transferability across datasets and sources.

Contribution

It introduces a method to incorporate dictionaries into neural networks for medical concept extraction, improving accuracy and transferability in COVID-19 related social media data.

Findings

Achieved 90% macro F1 score on forum data for concept extraction.

Obtained 81% F1 score on Twitter data using weakly labeled training.

Dictionaries improve model performance and transferability across datasets.

Abstract

We investigate the potential benefit of incorporating dictionary information into a neural network architecture for natural language processing. In particular, we make use of this architecture to extract several concepts related to COVID-19 from an on-line medical forum. We use a sample from the forum to manually curate one dictionary for each concept. In addition, we use MetaMap, which is a tool for extracting biomedical concepts, to identify a small number of semantic concepts. For a supervised concept extraction task on the forum data, our best model achieved a macro $F_1$ score of 90\%. A major difficulty in medical concept extraction is obtaining labelled data from which to build supervised models. We investigate the utility of our models to transfer to data derived from a different source in two ways. First for producing labels via weak learning and second to perform concept extraction. The dataset we use in this case comprises COVID-19 related tweets and we achieve an $F_1$ score 81\% for symptom concept extraction trained on weakly labelled data. The utility of our dictionaries is compared with a COVID-19 symptom dictionary that was constructed directly from Twitter. Further experiments that incorporate BERT and a COVID-19 version of BERTweet demonstrate that the dictionaries provide a commensurate result. Our results show that incorporating small domain dictionaries to deep learning models can improve concept extraction tasks. Moreover, models built using dictionaries generalize well and are transferable to different datasets on a similar task.